Towards Universal Backward-Compatible Representation Learning
Conventional model upgrades for visual search systems require offline refresh of gallery features by feeding gallery images into new models (dubbed as "backfill"), which is time-consuming and expensive, especially in large-scale applications. The task of backward-compatible representation learning is therefore introduced to support backfill-free model upgrades, where the new query features are interoperable with the old gallery features. Despite the success, previous works only investigated a close-set training scenario (i.e., the new training set shares the same classes as the old one), and are limited by more realistic and challenging open-set scenarios. To this end, we first introduce a new problem of universal backward-compatible representation learning, covering all possible data split in model upgrades. We further propose a simple yet effective method, dubbed as Universal Backward-Compatible Training (UniBCT) with a novel structural prototype refinement algorithm, to learn compatible representations in all kinds of model upgrading benchmarks in a unified manner. Comprehensive experiments on the large-scale face recognition datasets MS1Mv3 and IJB-C fully demonstrate the effectiveness of our method.
Code (3)
Tasks
Face RecognitionRepresentation LearningSimilar Papers 제목 키워드 기반
Towards Backward-Compatible Representation Learning
We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatib…
Face RecognitionRepresentation Learning$BT^2$: Backward-compatible Training with Basis Transformation
Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially costl…
RetrievalBT^2: Backward-compatible Training with Basis Transformation
Modern retrieval system often requires recomputing the representation of every piece of data in the gallery when updating to a better representation model. This process is known as backfilling and can be especially c…
Learning Backward Compatible Embeddings
Embeddings, low-dimensional vector representation of objects, are fundamental in building modern machine learning systems. In industrial settings, there is usually an embedding team that trains an embedding model to solv…
Fraud DetectionProduct RecommendationRecommendation SystemsBackward-Compatible Aligned Representations via an Orthogonal Transformation Layer
Visual retrieval systems face significant challenges when updating models with improved representations due to misalignment between the old and new representations. The costly and resource-intensive backfilling process i…